1 Which proteins are in the extracts?

  • hier wurde die Datenanalyse aller Extrakte statt mit dem Tribolium Fasta File mit Yeast und Triticum Aestivum durchgeführt, da dass das Medium für die Mehlwürmer war
  • Medium für die Käferzucht ist griffiges Weizenmehl mit 5% Hefeextrakt
  • es wurde dann gezählt wieviele der gefundenen Proteine Yeast (YEASX), Weizen (WHEAT) oder beides (YEASX/WHEAT) waren
    • YEASX/WHEAT: es gibt einige Proteine die sowohl in Weizen und Hefe vorkommen
  • der großteil der gefundenen Proteine ist Weizen
pth <- "X:/wissenschaftliche Veröffentlichungen/Publikationen/2022/Proteomics_JRS_DL/data/ta_yeast/results/"
filelist = list.files(path = pth, pattern = ".*.RDS")

for (file in filelist[grep("Razor",filelist)][-c(1,2)]){
  tmp <- readRDS(paste(pth,file,sep=""))
  tmp <- tmp[[1]]
  
  dat <- tmp
  yeasx <- grep("YEASX",dat$FASTA)
  wheat <- grep("WHEAT",dat$FASTA)
  # write human oder trica in a column
  for (i in 1:nrow(dat)){
    if (grepl("YEASX",dat$FASTA[i])){
      dat$org[i] <- "YEASX"
    }
    else if (grepl("WHEAT",dat$FASTA[i])){
      dat$org[i] <- "WHEAT"
    }
    else {
      dat$org[i] <- NA
    }
  }
  
  dat$org[intersect(yeasx,wheat)] <- "YEASX/WHEAT"
  
  dat4plot <- dat[,-c(ncol(dat)-1)]
  dat4plot_long <- melt(dat4plot, id = c("org"))
  tmp <- regmatches(dat4plot_long$variable,gregexpr("(?<=des.).*",dat4plot_long$variable,perl=TRUE))
  tmp <- unlist(tmp)
  dat4plot_long$variable <- tmp
  
  p <- ggplot(data=dat4plot_long, aes(x=variable, y=as.numeric(value), fill=org)) +
    stat_summary(fun.y = sum, geom = "bar", position = "dodge") +
    xlab("sample name") +
    ylab("counts") +
    theme(axis.text.x = element_text(angle = 90)) +
    labs(title = file)
  cat("\n")
  #cat(knit_print(ggplotly(p)))
  cat("##"," ",file,"\n")
  print(htmltools::tagList(ggplotly(p)))
  cat("\n")

if (print_fasta==TRUE){
for (i in 1:(ncol(dat)-2)){
  cat("\n")
  text <- paste(" Fasta Headers - Sample",unique(dat4plot_long$variable)[i])
  cat("###",text,"\n")
  cat("\"n")
  print(dat$FASTA[which(dat[,i])])
}
}
}

1.1 D2_ta_yeast_Razor.RDS

1.2 E3_D1_ta_yeast_Razor.RDS

1.3 E4_D1_a_j_ta_yeast_Razor.RDS

1.4 E4_D1_AF_TF_ta_yeast_Razor.RDS

1.5 E4_D1_B_ta_yeast_Razor.RDS

2 Relative comparison Tribolium (TC) with Triticum (TA)/YEAST

  • es wurde die relative häufigkeit von wheat/yeast bezogen auf die gesamten proteine die mit dem tribolium fasta file gefunden wurde berechnet und geplottet
  • das ganze wurde noch mit A. thaliana und Rat für zumindest D2 probiert
  • es zeigt, sich, dass auch in unseren Samples A.thaliana proteine und Rat proteine zu finden sind die wie bei Weizen/Yeast halt Proteine des allg. Stoffwechsels sind zB ATP-…., Histone,…
  • der Anteil liegt bei
    • 1-5% bei A. thaliana
    • 1-12% bei Rat
    • 1-7% bei Wheat/Yeast

\[%WHEAT/YEAST={number of proteins wheat/yeast} / {number of proteins tribolium}\]

# compare TC - ta/wheat
res_TC <- c(
  "results_run1_mqpar_extracts_2gether_E3_D1_combined_txt_proteinGroups.txt_summary.csv",
  "results_run1_mqpar_extracts_2gether_E4_D1_a-j_combined_txt_proteinGroups.txt_summary.csv",
  "results_run1_mqpar_extracts_2gether_D2_combined_txt_proteinGroups.txt_summary.csv",
  "results_run1_mqpar_extracts_2gether_E4_D1_B_combined_txt_proteinGroups.txt_summary.csv",
  "results_run1_mqpar_extracts_2gether_E4_D1_AF_TF_combined_txt_proteinGroups.txt_summary.csv")

res_ta_yeast <- c(
  "E3_D1_ta_yeast_summary.csv",
  "E4_D1_a_j_ta_yeast_summary.csv",
  "D2_ta_yeast_summary.csv",    
  "E4_D1_B_ta_yeast_summary.csv",
  "E4_D1_AF_TF_ta_yeast_summary.csv")

name_comp <- c(
  "E3_D1",
  "E4_D1_a_j",
  "D2",
  "E4_D1_B",
  "E4_D1_AF_TF")
plt <- htmltools::tagList()
for (i in 1:length(name_comp)){
  txt <- paste(" ",name_comp[i],sep="")
  cat("\n")
  cat("##",txt,"\n")
  cat("\n")
  TC <- read.csv2(paste("../results/",res_TC[i],sep=""))
  ta_yeast <- read.csv2(paste("./results/",res_ta_yeast[i],sep=""))
  comp <- ta_yeast/TC*100
  comp <- melt(comp[,c(2:25)])
  
  p <- ggplot(comp,aes(x = variable, y = value)) +
    geom_boxplot() + 
    xlab("Sample name") + 
    ylab("% Wheat/Triticum") +
    scale_x_discrete(labels = unique(tmp)) +
    theme(axis.text.x = element_text(angle = 90)) +
    labs(title = name_comp[i])
  plt[[i]] <- as.widget(ggplotly(p))
  cat(knit_print(ggplotly(p))) #https://stackoverflow.com/questions/48458390/how-to-print-html-interactive-plotly-graphs-within-a-lapply-loop-using-knitr-ren
  cat("\n")
}

2.1 E3_D1

2.2 E4_D1_a_j

2.3 D2

2.4 E4_D1_B

2.5 E4_D1_AF_TF

3 Compare TC with A. thaliana

# compare TC - ta/wheat
res_TC <- c(
  "results_run1_mqpar_extracts_2gether_D2_combined_txt_proteinGroups.txt_summary.csv")

res_athaliana <- c("D2_athaliana_summary.csv")

name_comp <- c("D2")
plt <- htmltools::tagList()
for (i in 1:length(name_comp)){
  txt <- paste(" ",name_comp[i],sep="")
  cat("\n")
  cat("##",txt,"\n")
  cat("\n")
  TC <- read.csv2(paste("../results/",res_TC[i],sep=""))
  athaliana <- read.csv2(paste("./results/",res_athaliana[i],sep=""))
  comp <- athaliana/TC*100
  comp <- melt(comp[,c(2:25)])
  
  p <- ggplot(comp,aes(x = variable, y = value)) +
    geom_boxplot() + 
    xlab("Sample name") + 
    ylab("% AThaliana/Triticum") +
    scale_x_discrete(labels = unique(tmp)) +
    theme(axis.text.x = element_text(angle = 90)) +
    labs(title = name_comp[i])
  plt[[i]] <- as.widget(ggplotly(p))
  cat(knit_print(ggplotly(p))) #https://stackoverflow.com/questions/48458390/how-to-print-html-interactive-plotly-graphs-within-a-lapply-loop-using-knitr-ren
  cat("\n")
}

3.1 D2

4 Compare TC with rat

# compare TC - ta/wheat
res_TC <- c(
  "results_run1_mqpar_extracts_2gether_D2_combined_txt_proteinGroups.txt_summary.csv")

res_rat <- c("D2_rat_summary.csv")

name_comp <- c("D2")
plt <- htmltools::tagList()
for (i in 1:length(name_comp)){
  txt <- paste(" ",name_comp[i],sep="")
  cat("\n")
  cat("##",txt,"\n")
  cat("\n")
  TC <- read.csv2(paste("../results/",res_TC[i],sep=""))
  rat <- read.csv2(paste("./results/",res_rat[i],sep=""))
  comp <- rat/TC*100
  comp <- melt(comp[,c(2:25)])
  
  p <- ggplot(comp,aes(x = variable, y = value)) +
    geom_boxplot() + 
    xlab("Sample name") + 
    ylab("% Rat/Triticum") +
    scale_x_discrete(labels = unique(tmp)) +
    theme(axis.text.x = element_text(angle = 90)) +
    labs(title = name_comp[i])
  plt[[i]] <- as.widget(ggplotly(p))
  cat(knit_print(ggplotly(p))) #https://stackoverflow.com/questions/48458390/how-to-print-html-interactive-plotly-graphs-within-a-lapply-loop-using-knitr-ren
  cat("\n")
}

4.1 D2